Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0766. Min Range: -8.0766
Max Act: 8.0766. Min Act: -0.1700
Data Index: 7013280 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.9829. Min Act: -0.1700
Data Index: 3135348 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7329. Min Act: -0.1700
Data Index: 3631830 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7329. Min Act: -0.1700
Data Index: 3818410 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7329. Min Act: -0.1700
Data Index: 1661072 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7016. Min Act: -0.1700
Data Index: 1009240 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6704. Min Act: -0.1700
Data Index: 8616600 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7016. Min Act: -0.1700
Data Index: 724260 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.7329. Min Act: -0.1700
Data Index: 6287473 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6704. Min Act: -0.1700
Data Index: 582773 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6391. Min Act: -0.1700
Data Index: 6287631 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6391. Min Act: -0.1700
Data Index: 5103314 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6391. Min Act: -0.1700
Data Index: 4640050 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6079. Min Act: -0.1700
Data Index: 1228178 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6079. Min Act: -0.1700
Data Index: 6287632 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6079. Min Act: -0.1700
Data Index: 1228179 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.6079. Min Act: -0.1700
Data Index: 1009239 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.5766. Min Act: -0.1700
Data Index: 1609423 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.5766. Min Act: -0.1700
Data Index: 5538037 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0766. Min Range: -8.0766
Max Act: 7.5454. Min Act: -0.1700
Data Index: 813159 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19